Body movement tracking

Patent metadata

Field	Value
Publication number	US-10646139-B2
Application number	US-201615369614-A
Country	US
Kind code	B2
Filing date	Dec 5, 2016
Priority date	Dec 5, 2016
Publication date	May 12, 2020
Grant date	May 12, 2020

Abstract

Disclosed methods, systems, and storage media may track body movements and movement trajectories using internal measurement units (IMUs), where a first IMU may be attached to a first wrist of a user, a second IMU may be attached to a second wrist of the user, and a third IMU may be attached to a torso of the user. Upper body movements may be derived from sensor data produced by the three IMUs. IMUs are typically not used to detect fine levels of body movements and/or movement trajectory because most IMUs accumulate errors due to large amounts of measurement noise. Embodiments provide arm and torso movement models to which the sensor data is applied in order to derive the body movements and/or movement trajectory. Additionally, estimation errors may be mitigated using a hidden Markov Model (HMM) filter. Other embodiments may be described and/or claimed.

First claim

The invention claimed is:

1. An apparatus comprising:
an acceleration engine (AE) arranged to determine, in a global coordinate system (GCS), a right wrist acceleration based on first sensor data, a left wrist acceleration based on second sensor data, and a torso acceleration based on third sensor data;
an orientation engine (OE) arranged to determine, in the GCS, a right wrist orientation based on the first sensor data, a left wrist orientation based on the second sensor data, and a torso orientation based on the third sensor data;
a relative motion engine (RME) arranged to;
determine a relative acceleration of a right elbow (RARE) based on the right wrist acceleration, the right wrist orientation, the torso acceleration, and the torso orientation, the RARE being acceleration of the right elbow relative to an acceleration of the torso, and
determine a relative acceleration of a left elbow (RALE) based on the left wrist acceleration, the left wrist orientation, the torso acceleration, and the torso orientation, the RALE being acceleration of the left elbow relative to the acceleration of the torso; and
a hidden Markov Model filter (HMMF) arranged to determine a relative position of the right elbow (RPRE) based on the determined RARE and a relative position of the left elbow (RPLE) based on the determined RALE.

2. The apparatus of claim 1 , wherein the AE is arranged to:
determine the right wrist acceleration in the GCS based on a reverse rotation of an acceleration component of the first sensor data and removal of a gravitational component from the acceleration component of the first sensor data;
determine the left wrist acceleration in the GCS based on a reverse rotation of an acceleration component of the second sensor data and removal of a gravitational component from the acceleration component of the second sensor data; and
determine the acceleration of the torso in the GCS based on a reverse rotation of an acceleration component of the third sensor data and removal of a gravitational component from the acceleration component of the third sensor data.

3. The apparatus of claim 1 , wherein the AE is arranged to:
determine a right forearm acceleration based on the right wrist acceleration and a right forearm length;
determine a right elbow acceleration based on the right forearm acceleration;
determine a left forearm acceleration based on the left wrist acceleration and a left forearm length; and
determine a left elbow acceleration based on the left forearm acceleration.

4. The apparatus of claim 3 , wherein the RME is arranged further to:
determine, based on the right elbow acceleration in the GCS, the right elbow orientation in the GCS, the torso acceleration in the GCS, and the torso orientation in the GCS, the RARE in a torso coordinate system (TCS), a relative right elbow velocity in the TCS, and a relative right elbow location in the TCS; and
determine, based on the left elbow acceleration in the GCS, the left elbow orientation in the GCS, the torso acceleration in the GCS, and the torso orientation in the GCS, the RALE in the TCS, a relative left elbow velocity in the TCS, and a relative left elbow location in the TCS.

5. The apparatus of claim 4 , wherein:
the RARE is an acceleration of the right elbow that is relative to the torso,
the relative right elbow velocity is a velocity of the right elbow relative to the torso,
the relative right elbow location is a location of the right elbow relative to the torso,
the RALE is an acceleration of the left elbow that is relative to the torso,
the relative left elbow velocity is a velocity of the left elbow relative to the torso, and
the relative left elbow location is a location of the left elbow relative to the torso.

6. The apparatus of claim 4 , further comprising:
a relative position engine (RPE) arranged to:
identify a right elbow search space (RESS) and a left elbow search space (LESS) based on an elbow model, the RESS including potential right elbow positions, and the LESS including potential left elbow positions;
determine a relative right elbow state (RRES) based on the right wrist acceleration and the right elbow acceleration, wherein the RRES corresponds to a point within the RESS; and
determine a relative left elbow state (RLES) based on the left wrist acceleration and the left elbow acceleration, wherein the RLES corresponds to a point within the LESS.

7. The apparatus of claim 1 , further comprising:
communications circuitry arranged to obtain the first sensor data from a first inertial measurement unit (IMU), obtain the second sensor data from a second IMU, and obtain the third sensor data from a third IMU,
wherein each of the first IMU, the second IMU, and the third IMU include a corresponding microelectromechanical system (MEMS) accelerometer, a MEMS gyroscope, and a MEMS magnetometer, and
wherein the first IMU is coupled with the right wrist, the second IMU is coupled with the left wrist, and the third IMU is coupled with the torso.

8. The apparatus of claim 1 , wherein the apparatus is implemented in a wearable computer device, a smartphone, a tablet personal computer (PC), a head-up display (HUD) device, a laptop PC, a desktop PC, or a server computer.

9. One or more non-transitory computer-readable media (NTCRM) comprising instructions, wherein execution of the instructions by one or more processors is to cause a computer device to:
determine, in a global coordinate system (GCS), a right wrist acceleration and right wrist orientation based on first sensor data, a left wrist acceleration and left wrist orientation based on second sensor data, and a torso acceleration and torso orientation based on third sensor data;
determine a relative acceleration of a right elbow (RARE) based on the right wrist acceleration, the right wrist orientation, the torso acceleration, and the torso orientation, and a relative acceleration of a left elbow (RALE) based on the left wrist acceleration, the left wrist orientation, the torso acceleration, and the torso orientation;
determine a relative position of the right elbow (RPRE) and a relative position of the left elbow (RPLE) based on the RARE and the RALE, respectively; and
control transmission of information to an application server, wherein the information is representative of a right arm position and orientation based on the RPRE and a left arm position and orientation based on the RPLE.

10. The one or more NTCRM of claim 9 , wherein execution of the instructions is to cause the computer device to:
determine the right wrist acceleration in the GCS based on a reverse rotation of an acceleration component of the first sensor data and removal of a gravitational component from the acceleration component of the first sensor data;
determine the left wrist acceleration in the GCS based on a reverse rotation of an acceleration component of the second sensor data and removal of a gravitational component from the acceleration component of the second sensor data; and
determine the acceleration of the torso in the GCS based on a reverse rotation of an acceleration component of the third sensor data and removal of a gravitational component from the acceleration component of the third sensor data.

11. The one or more NTCRM of claim 9 , wherein execution of the instructions is to cause the computer device to:
determine a right forearm acceleration based on the right wrist acceleration and a right forearm length;
determine a right elbow acceleration based on the right forearm acceleration;
determine a left forearm acceleration based on the left wrist acceleration and a left forearm length; and
determine a left elbow acceleration based on the left forear

Assignees

• Intel Corp

Inventors

• Yang Xue
• Shen Sheng
• Choudhury Romit Roy

Classifications

• G16H40/67

  for remote operation · CPC title

• A61B5/725

  using specific filters therefor, e.g. Kalman or adaptive filters (specific diagnostics methods using using bioelectric or biomagnetic signals A61B5/316) · CPC title

• A61B5/1112 Primary

  Global tracking of patients, e.g. by using GPS · CPC title

• A61B5/6824 Primary

  Arm or wrist · CPC title

• A61B5/0022

  Monitoring a patient using a global network, e.g. telephone networks, internet · CPC title